emergent-misalignment / emergent-misalignmentLinks
☆252Updated last week
Alternatives and similar repositories for emergent-misalignment
Users that are interested in emergent-misalignment are comparing it to the libraries listed below
Sorting:
- Open source interpretability artefacts for R1.☆167Updated 9 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆226Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆137Updated 11 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆329Updated 7 months ago
- Collection of evals for Inspect AI☆337Updated last week
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆330Updated 5 months ago
- METR Task Standard☆170Updated 11 months ago
- Improving Alignment and Robustness with Circuit Breakers☆254Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆236Updated last week
- https://transformer-circuits.pub/2025/attribution-graphs/methods.html☆91Updated 9 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆238Updated last year
- ☆151Updated 4 months ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆148Updated last week
- open source interpretability platform 🧠☆632Updated last week
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆131Updated last week
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆342Updated 2 weeks ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆161Updated 6 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆124Updated last year
- Sparsify transformers with SAEs and transcoders☆681Updated last week
- Steering Llama 2 with Contrastive Activation Addition☆206Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆289Updated last year
- ☆193Updated last year
- ☆550Updated 7 months ago
- ☆214Updated 3 weeks ago
- Inference API for many LLMs and other useful tools for empirical research☆98Updated 3 weeks ago
- Code for the paper "Fishing for Magikarp"☆178Updated 8 months ago
- ☆116Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Updated last year
- Mechanistic Interpretability Visualizations using React☆310Updated last year
- ⚖️ Awesome LLM Judges ⚖️☆148Updated 8 months ago